Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add akiotanaka847/qaio-desktop --skill set-up-trackinggit clone --depth 1 https://github.com/akiotanaka847/qaio-desktopWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/akiotanaka847/qaio-desktop/set-up-tracking)<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/set-up-tracking"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/set-up-tracking/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/akiotanaka847/qaio-desktop/set-up-tracking"><img src="https://agentmods.dev/badge/skills/akiotanaka847/qaio-desktop/set-up-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00067 | $0.02687 |
| Opus 5 | $0.00034 | $0.01344 |
| Sonnet 5 | $0.00013 | $0.00537 |
| Haiku 4.5 | $0.00007 | $0.00269 |
Grade A, and why
set-up-tracking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up Tracking
One skill for the tracking you need. scope param picks the shape: a single metric definition with daily snapshots, or a full dashboard spec (sections + visualizations + cadence + SQL per viz). Both write read-only SQL only and ground in your operating context.
Parameter: scope
metric- define a single metric, write the read-only SQL against your warehouse, snapshot the current value intometrics-daily.json, append the definition toconfig/metrics.json, and register it for the chosen cadence. Output: appendedconfig/metrics.json+metrics-daily.json+queries/{metric-slug}/.dashboard- propose 2-4 sections, per-section visualizations, cadence, and the read-only SQL behind each viz. Spec only - you or your BI tool renders. Output:config/dashboards.json(appended or updated by id).
User names scope in plain English ("track monthly revenue", "watch weekly active users", "spec a growth dashboard", "I want to see retention regularly") -> infer. Ambiguous -> ask ONE question naming both options.
When to use
metric:
- "start tracking {X}" / "add {metric} to the dashboard" / "watch {key metric}"
- A user-named metric on
onboard-mehas an emptysqlSnippetplaceholder, user invokes this skill to build the real definition.
dashboard:
- "spec me a dashboard for {X}"
- "I want to see {metric group} regularly"
- "build a dashboard for the {growth / retention / churn / revenue} team"
Connections I need
I run external work through Composio. Before this skill runs I check the categories below are linked. Missing -> I name the category, ask you to connect it from the Integrations tab, stop.
- Warehouse / data source (Postgres, BigQuery, Snowflake, Redshift) - Required for
scope=metric(I can't snapshot a metric without a source to read from). Optional forscope=dashboard(lets me write SQL snippets that run on your real schema; without it I leave parameterized placeholders). - Billing (Stripe) - Optional for
scope=metric. Lets me wire revenue metrics straight from billing instead of inferring from the warehouse.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 173 lines · 67 tokens per session scan A e9ab5a17b00a
set-up-tracking is a skill published in the GitHub repository akiotanaka847/qaio-desktop (2 stars, last pushed 8d ago), licensed MIT. It adds 67 tokens to every session and 2,687 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
forgetful-cli-setup
Set up the Forgetful CLI and connect from a terminal — install, local or remote mode, auth, and verification. Use when connecting a human or headless agent via shell, wiring CI with token auth, or operating a local server (serve, database selection, feature flags, re-embedding). Also covers the machine contract…
awslabs-timestream-for-influxdb-mcp
Time-series database operations.
awslabs-dynamodb-mcp
Complete DynamoDB operations and table management.
awslabs-elasticache-mcp
ElastiCache control plane operations.
epistemic-graph-migrations
Upgrade and migrate a live epistemic-graph engine (the AI-native database): binary version flips, the one-time snapshot/.mp -> redb authoritative migration, config/env migrations (e.g. retired GRAPHBACKEND values), and on-disk data-format evolution (bi-temporal fields, persisted blobs). Use when raising the engine…
data-tier-audit
Use when reviewing schemas, migrations, indexes, query plans, or data contract safety. USE FOR: audit schema drift, migration rollback safety, index health, query risk, repository patterns. DO NOT USE FOR: UI copywriting, infrastructure-only tasks, generic code review.